docs: list /wikiskill in README, docs/skills.md, and project structure

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AdmX6Jmuk2pkxCbSDiTv7e

Author: claude

CLAUDE.md

@@ -94,6 +94,7 @@ gstack/
 ├── cso/             # /cso skill (OWASP Top 10 + STRIDE security audit)
 ├── design-consultation/ # /design-consultation skill (design system from scratch)
 ├── setup-deploy/    # /setup-deploy skill (one-time deploy config)
+├── wikiskill/       # /wikiskill skill (WikiSkill self-evolution loop, arXiv:2608.27454)
 ├── .github/         # CI workflows + Docker image
 │   ├── workflows/   # evals.yml (E2E on Ubicloud), skill-docs.yml, actionlint.yml
 │   └── docker/      # Dockerfile.ci (pre-baked toolchain + Playwright/Chromium)

README.md

@@ -46,11 +46,11 @@ Fork it. Improve it. Make it yours. And if you want to hate on free open source
 
 Open Claude Code and paste this. Claude does the rest.
 
-> Install gstack: run **`git clone https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setup`** then add a "gstack" section to CLAUDE.md that says to use the /browse skill from gstack for all web browsing, never use mcp\_\_claude-in-chrome\_\_\* tools, and lists the available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse, /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /retro, /investigate, /document-release, /codex, /cso, /autoplan, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade. Then ask the user if they also want to add gstack to the current project so teammates get it.
+> Install gstack: run **`git clone https://github.com/garrytan/gstack.git ~/.claude/skills/gstack && cd ~/.claude/skills/gstack && ./setup`** then add a "gstack" section to CLAUDE.md that says to use the /browse skill from gstack for all web browsing, never use mcp\_\_claude-in-chrome\_\_\* tools, and lists the available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse, /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /retro, /investigate, /document-release, /codex, /cso, /autoplan, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade, /wikiskill. Then ask the user if they also want to add gstack to the current project so teammates get it.
 
 ### Step 2: Add to your repo so teammates get it (optional)
 
-> Add gstack to this project: run **`cp -Rf ~/.claude/skills/gstack .claude/skills/gstack && rm -rf .claude/skills/gstack/.git && cd .claude/skills/gstack && ./setup`** then add a "gstack" section to this project's CLAUDE.md that says to use the /browse skill from gstack for all web browsing, never use mcp\_\_claude-in-chrome\_\_\* tools, lists the available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse, /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /retro, /investigate, /document-release, /codex, /cso, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade, and tells Claude that if gstack skills aren't working, run `cd .claude/skills/gstack && ./setup` to build the binary and register skills.
+> Add gstack to this project: run **`cp -Rf ~/.claude/skills/gstack .claude/skills/gstack && rm -rf .claude/skills/gstack/.git && cd .claude/skills/gstack && ./setup`** then add a "gstack" section to this project's CLAUDE.md that says to use the /browse skill from gstack for all web browsing, never use mcp\_\_claude-in-chrome\_\_\* tools, lists the available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-design-review, /design-consultation, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse, /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /retro, /investigate, /document-release, /codex, /cso, /careful, /freeze, /guard, /unfreeze, /gstack-upgrade, /wikiskill, and tells Claude that if gstack skills aren't working, run `cd .claude/skills/gstack && ./setup` to build the binary and register skills.
 
 Real files get committed to your repo (not a submodule), so `git clone` just works. Everything lives inside `.claude/`. Nothing touches your PATH or runs in the background.
 
@@ -85,7 +85,7 @@ git clone https://github.com/garrytan/gstack.git ~/gstack
 cd ~/gstack && ./setup --host auto
 ```
 
-For Codex-compatible hosts, setup now supports both repo-local installs from `.agents/skills/gstack` and user-global installs from `~/.codex/skills/gstack`. All 28 skills work across all supported agents. Hook-based safety skills (careful, freeze, guard) use inline safety advisory prose on non-Claude hosts.
+For Codex-compatible hosts, setup now supports both repo-local installs from `.agents/skills/gstack` and user-global installs from `~/.codex/skills/gstack`. All 29 skills work across all supported agents. Hook-based safety skills (careful, freeze, guard) use inline safety advisory prose on non-Claude hosts.
 
 ## See it work
 
@@ -172,6 +172,7 @@ Each skill feeds into the next. `/office-hours` writes a design doc that `/plan-
 | `/unfreeze` | **Unlock** — remove the `/freeze` boundary. |
 | `/setup-deploy` | **Deploy Configurator** — one-time setup for `/land-and-deploy`. Detects your platform, production URL, and deploy commands. |
 | `/gstack-upgrade` | **Self-Updater** — upgrade gstack to latest. Detects global vs vendored install, syncs both, shows what changed. |
+| `/wikiskill` | **Skill Evolver** — run Google's WikiSkill loop with Claude Code as the worker: solve tasks, distill traces into a persistent wiki, propose a skill, keep it only if it beats validation. Accepted skills install straight into `~/.claude/skills/`. |
 
 **[Deep dives with examples and philosophy for every skill →](docs/skills.md)**
 
@@ -237,7 +238,7 @@ Available skills: /office-hours, /plan-ceo-review, /plan-eng-review, /plan-desig
 /design-consultation, /review, /ship, /land-and-deploy, /canary, /benchmark, /browse,
 /qa, /qa-only, /design-review, /setup-browser-cookies, /setup-deploy, /retro,
 /investigate, /document-release, /codex, /cso, /autoplan, /careful, /freeze, /guard,
-/unfreeze, /gstack-upgrade.
+/unfreeze, /gstack-upgrade, /wikiskill.
 ```
 
 ## License

docs/skills.md

@@ -30,6 +30,7 @@ Detailed guides for every gstack skill — philosophy, workflow, and examples.
 | [`/guard`](#safety--guardrails) | **Full Safety** | Combines /careful + /freeze in one command. Maximum safety for prod work. |
 | [`/unfreeze`](#safety--guardrails) | **Unlock** | Remove the /freeze boundary, allowing edits everywhere again. |
 | [`/gstack-upgrade`](#gstack-upgrade) | **Self-Updater** | Upgrade gstack to the latest version. Detects global vs vendored install, syncs both, shows what changed. |
+| [`/wikiskill`](#wikiskill) | **Skill Evolver** | Run the WikiSkill loop (arXiv:2608.27454) with Claude Code as the worker. Traces → wiki patterns → proposed skill → validation gate. Accepted skills install into `~/.claude/skills/`. |
 
 ---
 
@@ -818,6 +819,32 @@ Set `auto_upgrade: true` in `~/.gstack/config.yaml` to skip the prompt entirely
 
 ---
 
+## `/wikiskill`
+
+Let Claude Code evolve its own skills. `/wikiskill` wraps [WikiSkill](https://github.com/ashutoshsinghpr7/wikiskill) (Google Research, arXiv:2608.27454): the agent solves auto-graded tasks, a maintainer distills the traces into a persistent wiki of failure patterns, a proposer writes one candidate `SKILL.md`, and a gate keeps it only if it strictly beats the best validation score so far. The wiki is never rolled back; the skills only change when a change is proven.
+
+```
+You:   /wikiskill
+
+Claude: WikiSkill isn't installed yet — cloning to ~/.gstack/wikiskill and installing from source.
+        What do you want WikiSkill to do?
+        [Create a workspace] [Run the evolution loop] [Show status / results] [Transfer accepted skills]
+
+You:   Run the evolution loop, 3 iterations
+
+Claude: Workspace "demo" (13 train / 9 val), backend: claude
+        iter 1  baseline R_val=0.6667 → maintainer distilled 5 patterns → proposer created `find-secret`
+                gate: R_val=0.4444 — REJECTED (skill hurt 2 tasks). Rolled back; proposal kept in wiki/skill-impact.md
+        iter 2  proposer: no_action (nothing to gate)
+        iter 3  proposer patched `verify-output-readback` → gate: R_val=0.7778 — ACCEPTED (r_best 0.6667 → 0.7778)
+
+        1 accepted skill in skills/active/. Install it into ~/.claude/skills/?
+```
+
+Workspaces can live inside the wikiskill checkout or next to your project (`--ws .gstack/wikiskill/<name>`). Bring your own tasks by editing `tasks.json` — anything auto-gradable works (`exact`, `contains`, `json_field`, `code_stdout`). Accepted skills are standard SKILL.md packages, so they drop straight into Claude Code.
+
+---
+
 ## Greptile integration
 
 [Greptile](https://greptile.com) is a YC company that reviews your PRs automatically. It catches real bugs — race conditions, security issues, things that pass CI and blow up in production. It has genuinely saved my ass more than once. I love these guys.